Computer system management and throughput maximization in the presence of power constraints

Abstract

Methods are provided for maximizing the throughput of a computer system in the presence of one or more power constraints. Throughput is maximized by repeatedly or continuously or periodically optimizing task scheduling and assignment for each of a plurality of components of a computer system. The components include a plurality of central processing units (CPUs) each operating at a corresponding operating frequency. The components also include a plurality of disk drives. The corresponding operating frequencies of one or more CPUs of the plurality of CPUs are adjusted to maximize computer system throughput under one or more power constraints. Optimizing task scheduling and assignment, as well as adjusting the corresponding operating frequencies of one or more CPUs, are performed by solving a mathematical optimization problem using a first methodology over a first time interval and a second methodology over a second time interval longer than the first time interval. The first methodology comprises a short term heuristic solver for adapting to computer system changes that occur on a short time scale, and the second methodology comprises a long term solver having greater accuracy and greater computational complexity than the first methodology.

1. A method for maximizing throughput of a computer system in the presence of one or more power constraints, the method comprising:
 repeatedly or continuously or periodically optimizing task scheduling and assignment for each of a plurality of components of the computer system, wherein the components include a plurality of disk drives and a plurality of central processing units (CPUs) each operating at a corresponding operating frequency; and 
 adjusting the corresponding operating frequencies of one or more CPUs of the plurality of CPUs to maximize computer system throughput under one or more power constraints; 
 wherein said optimizing task scheduling and assignment, and said adjusting the corresponding operating frequencies of one or more CPUs, are performed by solving a mathematical optimization problem using a first methodology over a first time interval and a second methodology over a second time interval longer than the first time interval, and 
 wherein the first methodology comprises a short term heuristic solver for adapting to computer system changes that occur over the first time interval, and the second methodology comprises a long term solver for adapting to computer system changes that occur over the second time interval, wherein the second methodology has greater accuracy and greater computational complexity than the first methodology. 
 
     
     
       2. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes scheduling a first task to be performed by at least one of the plurality of CPUs simultaneously with a second task to be performed by at least one of the plurality of disk drives. 
     
     
       3. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes powering down at least one of the plurality of CPUs and scheduling a task to be performed by fewer CPUs of the plurality of CPUs. 
     
     
       4. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes powering down at least one of the plurality of disk drives and scheduling a task to be performed by fewer disk drives of the plurality of disk drives. 
     
     
       5. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes allocating a lower performing CPU of the plurality of CPUs to a task. 
     
     
       6. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes allocating a lower performing disk drive of the plurality of disk drives to a task. 
     
     
       7. The method of  claim 1  wherein said optimizing task scheduling and assignment further includes scheduling a first task and a second task to execute simultaneously on the plurality of CPUs. 
     
     
       8. The method of  claim 7  wherein the first and second tasks are independent. 
     
     
       9. The method of  claim 1  wherein a mixed integer linear program is employed to solve the mathematical optimization problem.